library(tidyverse)
## ── Attaching packages ─────────────────────────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2 ✓ purrr 0.3.4
## ✓ tibble 3.0.3 ✓ dplyr 1.0.2
## ✓ tidyr 1.1.2 ✓ stringr 1.4.0
## ✓ readr 1.3.1 ✓ forcats 0.5.0
## ── Conflicts ────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
Confirmed_State_6_13 <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/06-13-2020.csv")) %>%
filter(Country_Region == "US") %>%
group_by(Province_State, Country_Region) %>%
summarize(Confirmed = sum(Confirmed))
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_datetime(format = ""),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character(),
## Incidence_Rate = col_double(),
## `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` regrouping output by 'Province_State' (override with `.groups` argument)
str(Confirmed_State_6_13)
## tibble [58 × 3] (S3: grouped_df/tbl_df/tbl/data.frame)
## $ Province_State: chr [1:58] "Alabama" "Alaska" "Arizona" "Arkansas" ...
## $ Country_Region: chr [1:58] "US" "US" "US" "US" ...
## $ Confirmed : num [1:58] 24601 653 34660 12095 150018 ...
## - attr(*, "groups")= tibble [58 × 2] (S3: tbl_df/tbl/data.frame)
## ..$ Province_State: chr [1:58] "Alabama" "Alaska" "Arizona" "Arkansas" ...
## ..$ .rows : list<int> [1:58]
## .. ..$ : int 1
## .. ..$ : int 2
## .. ..$ : int 3
## .. ..$ : int 4
## .. ..$ : int 5
## .. ..$ : int 6
## .. ..$ : int 7
## .. ..$ : int 8
## .. ..$ : int 9
## .. ..$ : int 10
## .. ..$ : int 11
## .. ..$ : int 12
## .. ..$ : int 13
## .. ..$ : int 14
## .. ..$ : int 15
## .. ..$ : int 16
## .. ..$ : int 17
## .. ..$ : int 18
## .. ..$ : int 19
## .. ..$ : int 20
## .. ..$ : int 21
## .. ..$ : int 22
## .. ..$ : int 23
## .. ..$ : int 24
## .. ..$ : int 25
## .. ..$ : int 26
## .. ..$ : int 27
## .. ..$ : int 28
## .. ..$ : int 29
## .. ..$ : int 30
## .. ..$ : int 31
## .. ..$ : int 32
## .. ..$ : int 33
## .. ..$ : int 34
## .. ..$ : int 35
## .. ..$ : int 36
## .. ..$ : int 37
## .. ..$ : int 38
## .. ..$ : int 39
## .. ..$ : int 40
## .. ..$ : int 41
## .. ..$ : int 42
## .. ..$ : int 43
## .. ..$ : int 44
## .. ..$ : int 45
## .. ..$ : int 46
## .. ..$ : int 47
## .. ..$ : int 48
## .. ..$ : int 49
## .. ..$ : int 50
## .. ..$ : int 51
## .. ..$ : int 52
## .. ..$ : int 53
## .. ..$ : int 54
## .. ..$ : int 55
## .. ..$ : int 56
## .. ..$ : int 57
## .. ..$ : int 58
## .. ..@ ptype: int(0)
## ..- attr(*, ".drop")= logi TRUE
Confirmed_State_9_13 <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-13-2020.csv")) %>%
filter(Country_Region == "US") %>%
group_by(Province_State, Country_Region) %>%
summarize(Confirmed = sum(Confirmed))
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_datetime(format = ""),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character(),
## Incidence_Rate = col_double(),
## `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` regrouping output by 'Province_State' (override with `.groups` argument)
setdiff(Confirmed_State_9_13$Province_State, Confirmed_State_6_13$Province_State)
## character(0)
Confirmed_State_9_13 <- Confirmed_State_9_13 %>%
filter(Province_State != "Recovered")
Confirmed_State_6_13 <- Confirmed_State_6_13 %>%
filter(Province_State != "Recovered")
Confirmed_State_6_13_9_13_joined <- full_join(Confirmed_State_6_13, Confirmed_State_9_13, by = c("Province_State"))
head(Confirmed_State_6_13_9_13_joined)
## # A tibble: 6 x 5
## # Groups: Province_State [6]
## Province_State Country_Region.x Confirmed.x Country_Region.y Confirmed.y
## <chr> <chr> <dbl> <chr> <dbl>
## 1 Alabama US 24601 US 138755
## 2 Alaska US 653 US 6268
## 3 Arizona US 34660 US 208512
## 4 Arkansas US 12095 US 70219
## 5 California US 150018 US 761728
## 6 Colorado US 29002 US 61293
tail(Confirmed_State_6_13_9_13_joined)
## # A tibble: 6 x 5
## # Groups: Province_State [6]
## Province_State Country_Region.x Confirmed.x Country_Region.y Confirmed.y
## <chr> <chr> <dbl> <chr> <dbl>
## 1 Virgin Islands US 72 US 1220
## 2 Virginia US 53869 US 133742
## 3 Washington US 25538 US 79826
## 4 West Virginia US 2274 US 12705
## 5 Wisconsin US 22518 US 89185
## 6 Wyoming US 1050 US 4346
which(is.na(Confirmed_State_6_13_9_13_joined))
## integer(0)
Confirmed_State_6_13_9_13_joined <- full_join(Confirmed_State_6_13,
Confirmed_State_9_13, by = c("Province_State")) %>%
rename(Confirmed_6_13_2020 = "Confirmed.x", Confirmed_9_13_2020 = "Confirmed.y") %>%
select(-Country_Region.x, -Country_Region.y) %>%
replace_na(list(Confirmed_6_13_2020 = 0))
head(Confirmed_State_6_13_9_13_joined)
## # A tibble: 6 x 3
## # Groups: Province_State [6]
## Province_State Confirmed_6_13_2020 Confirmed_9_13_2020
## <chr> <dbl> <dbl>
## 1 Alabama 24601 138755
## 2 Alaska 653 6268
## 3 Arizona 34660 208512
## 4 Arkansas 12095 70219
## 5 California 150018 761728
## 6 Colorado 29002 61293
which(is.na(Confirmed_State_6_13_9_13_joined))
## integer(0)
Confirmed_State_6_13_9_13_joined_long <- Confirmed_State_6_13_9_13_joined %>%
pivot_longer(-c(Province_State),
names_to = "Date", values_to = "Confirmed")
head(Confirmed_State_6_13_9_13_joined_long)
## # A tibble: 6 x 3
## # Groups: Province_State [3]
## Province_State Date Confirmed
## <chr> <chr> <dbl>
## 1 Alabama Confirmed_6_13_2020 24601
## 2 Alabama Confirmed_9_13_2020 138755
## 3 Alaska Confirmed_6_13_2020 653
## 4 Alaska Confirmed_9_13_2020 6268
## 5 Arizona Confirmed_6_13_2020 34660
## 6 Arizona Confirmed_9_13_2020 208512
ggplot(data= Confirmed_State_6_13_9_13_joined_long, aes(x= Confirmed, y= Province_State)) +
geom_point(aes(color= Date)) +
theme(axis.text.x = element_text(colour = "grey20", size = 12, angle = 90, hjust = 0.5, vjust = 0.5), axis.text.y = element_text(colour = "grey20", size = 6), strip.text = element_text(face = "italic"), text = element_text(size = 16))
Question 2
Confirmed_in_US_States_joined_long <- Confirmed_State_6_13_9_13_joined_long %>%
group_by(Province_State)
ggplot(data= Confirmed_in_US_States_joined_long, aes(x= Province_State, y= Confirmed)) +
geom_col(aes(color= Date)) +
theme(axis.text.x = element_text(colour = "grey20", size = 20, angle = 90, hjust = 0.75, vjust = 0.75), axis.text.y = element_text(colour = "grey20", size = 20), strip.text = element_text(face = "italic"), text = element_text(size = 16), axis.title.x = element_text(size= 30), axis.title.y = element_text(size= 30), plot.title = element_text(size = 35)) +
labs(title = "Bar plot of US States vs Confirmed Cases") +
xlab("US states") +
ylab("Confirmed Cases")
time_series_confirmed <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv")) %>%
rename(Province_State = "Province/State", Country_Region = "Country/Region")
## Parsed with column specification:
## cols(
## .default = col_double(),
## `Province/State` = col_character(),
## `Country/Region` = col_character()
## )
## See spec(...) for full column specifications.
head(time_series_confirmed)
## # A tibble: 6 x 249
## Province_State Country_Region Lat Long `1/22/20` `1/23/20` `1/24/20`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 0 0 0
## 2 <NA> Albania 41.2 20.2 0 0 0
## 3 <NA> Algeria 28.0 1.66 0 0 0
## 4 <NA> Andorra 42.5 1.52 0 0 0
## 5 <NA> Angola -11.2 17.9 0 0 0
## 6 <NA> Antigua and B… 17.1 -61.8 0 0 0
## # … with 242 more variables: `1/25/20` <dbl>, `1/26/20` <dbl>, `1/27/20` <dbl>,
## # `1/28/20` <dbl>, `1/29/20` <dbl>, `1/30/20` <dbl>, `1/31/20` <dbl>,
## # `2/1/20` <dbl>, `2/2/20` <dbl>, `2/3/20` <dbl>, `2/4/20` <dbl>,
## # `2/5/20` <dbl>, `2/6/20` <dbl>, `2/7/20` <dbl>, `2/8/20` <dbl>,
## # `2/9/20` <dbl>, `2/10/20` <dbl>, `2/11/20` <dbl>, `2/12/20` <dbl>,
## # `2/13/20` <dbl>, `2/14/20` <dbl>, `2/15/20` <dbl>, `2/16/20` <dbl>,
## # `2/17/20` <dbl>, `2/18/20` <dbl>, `2/19/20` <dbl>, `2/20/20` <dbl>,
## # `2/21/20` <dbl>, `2/22/20` <dbl>, `2/23/20` <dbl>, `2/24/20` <dbl>,
## # `2/25/20` <dbl>, `2/26/20` <dbl>, `2/27/20` <dbl>, `2/28/20` <dbl>,
## # `2/29/20` <dbl>, `3/1/20` <dbl>, `3/2/20` <dbl>, `3/3/20` <dbl>,
## # `3/4/20` <dbl>, `3/5/20` <dbl>, `3/6/20` <dbl>, `3/7/20` <dbl>,
## # `3/8/20` <dbl>, `3/9/20` <dbl>, `3/10/20` <dbl>, `3/11/20` <dbl>,
## # `3/12/20` <dbl>, `3/13/20` <dbl>, `3/14/20` <dbl>, `3/15/20` <dbl>,
## # `3/16/20` <dbl>, `3/17/20` <dbl>, `3/18/20` <dbl>, `3/19/20` <dbl>,
## # `3/20/20` <dbl>, `3/21/20` <dbl>, `3/22/20` <dbl>, `3/23/20` <dbl>,
## # `3/24/20` <dbl>, `3/25/20` <dbl>, `3/26/20` <dbl>, `3/27/20` <dbl>,
## # `3/28/20` <dbl>, `3/29/20` <dbl>, `3/30/20` <dbl>, `3/31/20` <dbl>,
## # `4/1/20` <dbl>, `4/2/20` <dbl>, `4/3/20` <dbl>, `4/4/20` <dbl>,
## # `4/5/20` <dbl>, `4/6/20` <dbl>, `4/7/20` <dbl>, `4/8/20` <dbl>,
## # `4/9/20` <dbl>, `4/10/20` <dbl>, `4/11/20` <dbl>, `4/12/20` <dbl>,
## # `4/13/20` <dbl>, `4/14/20` <dbl>, `4/15/20` <dbl>, `4/16/20` <dbl>,
## # `4/17/20` <dbl>, `4/18/20` <dbl>, `4/19/20` <dbl>, `4/20/20` <dbl>,
## # `4/21/20` <dbl>, `4/22/20` <dbl>, `4/23/20` <dbl>, `4/24/20` <dbl>,
## # `4/25/20` <dbl>, `4/26/20` <dbl>, `4/27/20` <dbl>, `4/28/20` <dbl>,
## # `4/29/20` <dbl>, `4/30/20` <dbl>, `5/1/20` <dbl>, `5/2/20` <dbl>,
## # `5/3/20` <dbl>, …
time_series_confirmed_long <- time_series_confirmed %>%
pivot_longer(-c(Province_State, Country_Region, Lat, Long), names_to = "Date", values_to = "Confirmed")
head(time_series_confirmed_long)
## # A tibble: 6 x 6
## Province_State Country_Region Lat Long Date Confirmed
## <chr> <chr> <dbl> <dbl> <chr> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 1/22/20 0
## 2 <NA> Afghanistan 33.9 67.7 1/23/20 0
## 3 <NA> Afghanistan 33.9 67.7 1/24/20 0
## 4 <NA> Afghanistan 33.9 67.7 1/25/20 0
## 5 <NA> Afghanistan 33.9 67.7 1/26/20 0
## 6 <NA> Afghanistan 33.9 67.7 1/27/20 0
download.file(url="https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv", destfile = "data/time_series_covid19_deaths_global.csv")
time_series_deaths <- read_csv("data/time_series_covid19_deaths_global.csv")%>%
rename(Province_State = "Province/State", Country_Region = "Country/Region")
## Parsed with column specification:
## cols(
## .default = col_double(),
## `Province/State` = col_character(),
## `Country/Region` = col_character()
## )
## See spec(...) for full column specifications.
head(time_series_deaths)
## # A tibble: 6 x 249
## Province_State Country_Region Lat Long `1/22/20` `1/23/20` `1/24/20`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 0 0 0
## 2 <NA> Albania 41.2 20.2 0 0 0
## 3 <NA> Algeria 28.0 1.66 0 0 0
## 4 <NA> Andorra 42.5 1.52 0 0 0
## 5 <NA> Angola -11.2 17.9 0 0 0
## 6 <NA> Antigua and B… 17.1 -61.8 0 0 0
## # … with 242 more variables: `1/25/20` <dbl>, `1/26/20` <dbl>, `1/27/20` <dbl>,
## # `1/28/20` <dbl>, `1/29/20` <dbl>, `1/30/20` <dbl>, `1/31/20` <dbl>,
## # `2/1/20` <dbl>, `2/2/20` <dbl>, `2/3/20` <dbl>, `2/4/20` <dbl>,
## # `2/5/20` <dbl>, `2/6/20` <dbl>, `2/7/20` <dbl>, `2/8/20` <dbl>,
## # `2/9/20` <dbl>, `2/10/20` <dbl>, `2/11/20` <dbl>, `2/12/20` <dbl>,
## # `2/13/20` <dbl>, `2/14/20` <dbl>, `2/15/20` <dbl>, `2/16/20` <dbl>,
## # `2/17/20` <dbl>, `2/18/20` <dbl>, `2/19/20` <dbl>, `2/20/20` <dbl>,
## # `2/21/20` <dbl>, `2/22/20` <dbl>, `2/23/20` <dbl>, `2/24/20` <dbl>,
## # `2/25/20` <dbl>, `2/26/20` <dbl>, `2/27/20` <dbl>, `2/28/20` <dbl>,
## # `2/29/20` <dbl>, `3/1/20` <dbl>, `3/2/20` <dbl>, `3/3/20` <dbl>,
## # `3/4/20` <dbl>, `3/5/20` <dbl>, `3/6/20` <dbl>, `3/7/20` <dbl>,
## # `3/8/20` <dbl>, `3/9/20` <dbl>, `3/10/20` <dbl>, `3/11/20` <dbl>,
## # `3/12/20` <dbl>, `3/13/20` <dbl>, `3/14/20` <dbl>, `3/15/20` <dbl>,
## # `3/16/20` <dbl>, `3/17/20` <dbl>, `3/18/20` <dbl>, `3/19/20` <dbl>,
## # `3/20/20` <dbl>, `3/21/20` <dbl>, `3/22/20` <dbl>, `3/23/20` <dbl>,
## # `3/24/20` <dbl>, `3/25/20` <dbl>, `3/26/20` <dbl>, `3/27/20` <dbl>,
## # `3/28/20` <dbl>, `3/29/20` <dbl>, `3/30/20` <dbl>, `3/31/20` <dbl>,
## # `4/1/20` <dbl>, `4/2/20` <dbl>, `4/3/20` <dbl>, `4/4/20` <dbl>,
## # `4/5/20` <dbl>, `4/6/20` <dbl>, `4/7/20` <dbl>, `4/8/20` <dbl>,
## # `4/9/20` <dbl>, `4/10/20` <dbl>, `4/11/20` <dbl>, `4/12/20` <dbl>,
## # `4/13/20` <dbl>, `4/14/20` <dbl>, `4/15/20` <dbl>, `4/16/20` <dbl>,
## # `4/17/20` <dbl>, `4/18/20` <dbl>, `4/19/20` <dbl>, `4/20/20` <dbl>,
## # `4/21/20` <dbl>, `4/22/20` <dbl>, `4/23/20` <dbl>, `4/24/20` <dbl>,
## # `4/25/20` <dbl>, `4/26/20` <dbl>, `4/27/20` <dbl>, `4/28/20` <dbl>,
## # `4/29/20` <dbl>, `4/30/20` <dbl>, `5/1/20` <dbl>, `5/2/20` <dbl>,
## # `5/3/20` <dbl>, …
time_series_deaths_long <- time_series_deaths %>%
pivot_longer(-c(Province_State, Country_Region, Lat, Long), names_to = "Date", values_to = "Deaths")
head(time_series_deaths_long)
## # A tibble: 6 x 6
## Province_State Country_Region Lat Long Date Deaths
## <chr> <chr> <dbl> <dbl> <chr> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 1/22/20 0
## 2 <NA> Afghanistan 33.9 67.7 1/23/20 0
## 3 <NA> Afghanistan 33.9 67.7 1/24/20 0
## 4 <NA> Afghanistan 33.9 67.7 1/25/20 0
## 5 <NA> Afghanistan 33.9 67.7 1/26/20 0
## 6 <NA> Afghanistan 33.9 67.7 1/27/20 0
time_series_confirmed_long <- time_series_confirmed_long %>%
unite(Key, Province_State, Country_Region, Date, sep = ".", remove = FALSE)
head(time_series_confirmed_long)
## # A tibble: 6 x 7
## Key Province_State Country_Region Lat Long Date Confirmed
## <chr> <chr> <chr> <dbl> <dbl> <chr> <dbl>
## 1 NA.Afghanistan.1/2… <NA> Afghanistan 33.9 67.7 1/22/… 0
## 2 NA.Afghanistan.1/2… <NA> Afghanistan 33.9 67.7 1/23/… 0
## 3 NA.Afghanistan.1/2… <NA> Afghanistan 33.9 67.7 1/24/… 0
## 4 NA.Afghanistan.1/2… <NA> Afghanistan 33.9 67.7 1/25/… 0
## 5 NA.Afghanistan.1/2… <NA> Afghanistan 33.9 67.7 1/26/… 0
## 6 NA.Afghanistan.1/2… <NA> Afghanistan 33.9 67.7 1/27/… 0
time_series_deaths_long <- time_series_deaths_long %>%
unite(Key, Province_State, Country_Region, Date, sep = ".") %>%
select(Key, Deaths)
head(time_series_deaths_long)
## # A tibble: 6 x 2
## Key Deaths
## <chr> <dbl>
## 1 NA.Afghanistan.1/22/20 0
## 2 NA.Afghanistan.1/23/20 0
## 3 NA.Afghanistan.1/24/20 0
## 4 NA.Afghanistan.1/25/20 0
## 5 NA.Afghanistan.1/26/20 0
## 6 NA.Afghanistan.1/27/20 0
time_series_long_joined <- full_join(time_series_confirmed_long, time_series_deaths_long, by= c("Key")) %>%
select(-Key)
time_series_long_joined
## # A tibble: 65,170 x 7
## Province_State Country_Region Lat Long Date Confirmed Deaths
## <chr> <chr> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 1/22/20 0 0
## 2 <NA> Afghanistan 33.9 67.7 1/23/20 0 0
## 3 <NA> Afghanistan 33.9 67.7 1/24/20 0 0
## 4 <NA> Afghanistan 33.9 67.7 1/25/20 0 0
## 5 <NA> Afghanistan 33.9 67.7 1/26/20 0 0
## 6 <NA> Afghanistan 33.9 67.7 1/27/20 0 0
## 7 <NA> Afghanistan 33.9 67.7 1/28/20 0 0
## 8 <NA> Afghanistan 33.9 67.7 1/29/20 0 0
## 9 <NA> Afghanistan 33.9 67.7 1/30/20 0 0
## 10 <NA> Afghanistan 33.9 67.7 1/31/20 0 0
## # … with 65,160 more rows
which(is.na(time_series_long_joined$Confirmed))
## integer(0)
which(is.na(time_series_long_joined$Deaths))
## integer(0)
library(lubridate)
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
time_series_long_joined$Date <- mdy(time_series_long_joined$Date)
time_series_long_joined_counts <- time_series_long_joined %>%
pivot_longer(-c(Province_State, Country_Region, Lat, Long, Date), names_to = "Report_Type", values_to = "Counts")
head(time_series_long_joined_counts)
## # A tibble: 6 x 7
## Province_State Country_Region Lat Long Date Report_Type Counts
## <chr> <chr> <dbl> <dbl> <date> <chr> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 2020-01-22 Confirmed 0
## 2 <NA> Afghanistan 33.9 67.7 2020-01-22 Deaths 0
## 3 <NA> Afghanistan 33.9 67.7 2020-01-23 Confirmed 0
## 4 <NA> Afghanistan 33.9 67.7 2020-01-23 Deaths 0
## 5 <NA> Afghanistan 33.9 67.7 2020-01-24 Confirmed 0
## 6 <NA> Afghanistan 33.9 67.7 2020-01-24 Deaths 0
head(time_series_long_joined_counts)
## # A tibble: 6 x 7
## Province_State Country_Region Lat Long Date Report_Type Counts
## <chr> <chr> <dbl> <dbl> <date> <chr> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 2020-01-22 Confirmed 0
## 2 <NA> Afghanistan 33.9 67.7 2020-01-22 Deaths 0
## 3 <NA> Afghanistan 33.9 67.7 2020-01-23 Confirmed 0
## 4 <NA> Afghanistan 33.9 67.7 2020-01-23 Deaths 0
## 5 <NA> Afghanistan 33.9 67.7 2020-01-24 Confirmed 0
## 6 <NA> Afghanistan 33.9 67.7 2020-01-24 Deaths 0
Question 4
time_series_long_joined_counts %>%
group_by(Date) %>%
filter (Report_Type == "Deaths") %>%
ggplot(aes(x = Date, y= Counts)) +
geom_col() +
geom_line() +
ggtitle("Worldwide Confiremd Deaths per day") +
xlab("Per Day") +
ylab("Totals Confirmed Deaths")
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region %in% c("China","Japan", "Korea, South",
"Italy","Spain", "US")) %>%
ggplot(aes(x = Date, y = Deaths)) +
geom_point() +
geom_line() +
ggtitle("COVID-19 Deaths") +
facet_wrap(~Country_Region, ncol=2, scales="free_y")
# 6
head(time_series_long_joined)
## # A tibble: 6 x 7
## Province_State Country_Region Lat Long Date Confirmed Deaths
## <chr> <chr> <dbl> <dbl> <date> <dbl> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 2020-01-22 0 0
## 2 <NA> Afghanistan 33.9 67.7 2020-01-23 0 0
## 3 <NA> Afghanistan 33.9 67.7 2020-01-24 0 0
## 4 <NA> Afghanistan 33.9 67.7 2020-01-25 0 0
## 5 <NA> Afghanistan 33.9 67.7 2020-01-26 0 0
## 6 <NA> Afghanistan 33.9 67.7 2020-01-27 0 0
Question 6A: Total Deaths
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region == "US") %>%
ggplot(aes(x = Date, y = log2(Deaths), color = Deaths)) +
geom_point() +
geom_line() +
ggtitle("US COVID-19 Deaths per Day") +
xlab("per Day") +
ylab("log2(Total Deaths)")
Question 6B: Total Confirmed
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region == "US") %>%
ggplot(aes(x = Date, y = log2(Confirmed), color = Confirmed)) +
geom_point() +
geom_line() +
ggtitle("US COVID-19 Confirmed") +
xlab("per Day") +
ylab("lohg2(Total Confirmed)")
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region %in% c("China","Japan", "Korea, South",
"Italy","Spain", "US")) %>%
ggplot(aes(x = Date, y = Deaths)) +
geom_point() +
geom_line() +
ggtitle("COVID-19 Deaths") +
facet_wrap(~Country_Region, ncol=2, scales="free_y")
head(time_series_long_joined)
## # A tibble: 6 x 7
## Province_State Country_Region Lat Long Date Confirmed Deaths
## <chr> <chr> <dbl> <dbl> <date> <dbl> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 2020-01-22 0 0
## 2 <NA> Afghanistan 33.9 67.7 2020-01-23 0 0
## 3 <NA> Afghanistan 33.9 67.7 2020-01-24 0 0
## 4 <NA> Afghanistan 33.9 67.7 2020-01-25 0 0
## 5 <NA> Afghanistan 33.9 67.7 2020-01-26 0 0
## 6 <NA> Afghanistan 33.9 67.7 2020-01-27 0 0
top10_countries_time_series_long_joined <- time_series_long_joined %>%
group_by(`Country_Region`) %>%
summarize(Deaths = sum(Deaths)) %>%
arrange(desc(Deaths)) %>%
slice(1:10)
## `summarise()` ungrouping output (override with `.groups` argument)
top10_countries_time_series_long_joined
## # A tibble: 10 x 2
## Country_Region Deaths
## <chr> <dbl>
## 1 US 21282360
## 2 Brazil 10519674
## 3 United Kingdom 6156590
## 4 Italy 5726655
## 5 Mexico 5201319
## 6 France 4793527
## 7 Spain 4693751
## 8 India 4551683
## 9 Iran 2202060
## 10 Peru 2153636
Question 7
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region %in% c("US", "Brazil","United Kingdom", "Italy", "Mexico", "France","Spain", "India", "Iran", "Peru")) %>%
ggplot(aes(x = Date, y = Deaths, color = Country_Region)) +
geom_point() +
geom_line() +
ggtitle("Countries with top 10 COVID-19 Deaths") +
xlab("per Day") +
ylab("Total Deaths")
head(time_series_long_joined)
## # A tibble: 6 x 7
## Province_State Country_Region Lat Long Date Confirmed Deaths
## <chr> <chr> <dbl> <dbl> <date> <dbl> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 2020-01-22 0 0
## 2 <NA> Afghanistan 33.9 67.7 2020-01-23 0 0
## 3 <NA> Afghanistan 33.9 67.7 2020-01-24 0 0
## 4 <NA> Afghanistan 33.9 67.7 2020-01-25 0 0
## 5 <NA> Afghanistan 33.9 67.7 2020-01-26 0 0
## 6 <NA> Afghanistan 33.9 67.7 2020-01-27 0 0
Question 8
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region %in% c("US", "Brazil","United Kingdom", "Italy", "Mexico", "France","Spain", "India", "Iran", "Peru")) %>%
ggplot(aes(x = Date, y = Deaths, color = Country_Region)) +
geom_point() +
geom_line() +
ggtitle("Countries with top 10 COVID-19 Deaths") +
facet_wrap(~Country_Region, ncol=2, scales="free_y") +
theme(axis.text.x = element_text(colour = "red", size = 8, hjust = 2, vjust = 2), axis.text.y = element_text(colour = "red", size = 6), strip.text = element_text(face = "italic"), text = element_text(size = 15), axis.title.x = element_text(size = 20), axis.title.y = element_text(size = 20), plot.title = element_text(size = 20, face = "bold"))
time_series_confirmed_USA <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_US.csv"))
## Parsed with column specification:
## cols(
## .default = col_double(),
## iso2 = col_character(),
## iso3 = col_character(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Combined_Key = col_character()
## )
## See spec(...) for full column specifications.
head(time_series_confirmed_USA)
## # A tibble: 6 x 256
## UID iso2 iso3 code3 FIPS Admin2 Province_State Country_Region Lat
## <dbl> <chr> <chr> <dbl> <dbl> <chr> <chr> <chr> <dbl>
## 1 8.40e7 US USA 840 1001 Autau… Alabama US 32.5
## 2 8.40e7 US USA 840 1003 Baldw… Alabama US 30.7
## 3 8.40e7 US USA 840 1005 Barbo… Alabama US 31.9
## 4 8.40e7 US USA 840 1007 Bibb Alabama US 33.0
## 5 8.40e7 US USA 840 1009 Blount Alabama US 34.0
## 6 8.40e7 US USA 840 1011 Bullo… Alabama US 32.1
## # … with 247 more variables: Long_ <dbl>, Combined_Key <chr>, `1/22/20` <dbl>,
## # `1/23/20` <dbl>, `1/24/20` <dbl>, `1/25/20` <dbl>, `1/26/20` <dbl>,
## # `1/27/20` <dbl>, `1/28/20` <dbl>, `1/29/20` <dbl>, `1/30/20` <dbl>,
## # `1/31/20` <dbl>, `2/1/20` <dbl>, `2/2/20` <dbl>, `2/3/20` <dbl>,
## # `2/4/20` <dbl>, `2/5/20` <dbl>, `2/6/20` <dbl>, `2/7/20` <dbl>,
## # `2/8/20` <dbl>, `2/9/20` <dbl>, `2/10/20` <dbl>, `2/11/20` <dbl>,
## # `2/12/20` <dbl>, `2/13/20` <dbl>, `2/14/20` <dbl>, `2/15/20` <dbl>,
## # `2/16/20` <dbl>, `2/17/20` <dbl>, `2/18/20` <dbl>, `2/19/20` <dbl>,
## # `2/20/20` <dbl>, `2/21/20` <dbl>, `2/22/20` <dbl>, `2/23/20` <dbl>,
## # `2/24/20` <dbl>, `2/25/20` <dbl>, `2/26/20` <dbl>, `2/27/20` <dbl>,
## # `2/28/20` <dbl>, `2/29/20` <dbl>, `3/1/20` <dbl>, `3/2/20` <dbl>,
## # `3/3/20` <dbl>, `3/4/20` <dbl>, `3/5/20` <dbl>, `3/6/20` <dbl>,
## # `3/7/20` <dbl>, `3/8/20` <dbl>, `3/9/20` <dbl>, `3/10/20` <dbl>,
## # `3/11/20` <dbl>, `3/12/20` <dbl>, `3/13/20` <dbl>, `3/14/20` <dbl>,
## # `3/15/20` <dbl>, `3/16/20` <dbl>, `3/17/20` <dbl>, `3/18/20` <dbl>,
## # `3/19/20` <dbl>, `3/20/20` <dbl>, `3/21/20` <dbl>, `3/22/20` <dbl>,
## # `3/23/20` <dbl>, `3/24/20` <dbl>, `3/25/20` <dbl>, `3/26/20` <dbl>,
## # `3/27/20` <dbl>, `3/28/20` <dbl>, `3/29/20` <dbl>, `3/30/20` <dbl>,
## # `3/31/20` <dbl>, `4/1/20` <dbl>, `4/2/20` <dbl>, `4/3/20` <dbl>,
## # `4/4/20` <dbl>, `4/5/20` <dbl>, `4/6/20` <dbl>, `4/7/20` <dbl>,
## # `4/8/20` <dbl>, `4/9/20` <dbl>, `4/10/20` <dbl>, `4/11/20` <dbl>,
## # `4/12/20` <dbl>, `4/13/20` <dbl>, `4/14/20` <dbl>, `4/15/20` <dbl>,
## # `4/16/20` <dbl>, `4/17/20` <dbl>, `4/18/20` <dbl>, `4/19/20` <dbl>,
## # `4/20/20` <dbl>, `4/21/20` <dbl>, `4/22/20` <dbl>, `4/23/20` <dbl>,
## # `4/24/20` <dbl>, `4/25/20` <dbl>, `4/26/20` <dbl>, `4/27/20` <dbl>,
## # `4/28/20` <dbl>, …
time_series_confirmed_USA %>%
group_by(Province_State)
## # A tibble: 3,340 x 256
## # Groups: Province_State [58]
## UID iso2 iso3 code3 FIPS Admin2 Province_State Country_Region Lat
## <dbl> <chr> <chr> <dbl> <dbl> <chr> <chr> <chr> <dbl>
## 1 8.40e7 US USA 840 1001 Autau… Alabama US 32.5
## 2 8.40e7 US USA 840 1003 Baldw… Alabama US 30.7
## 3 8.40e7 US USA 840 1005 Barbo… Alabama US 31.9
## 4 8.40e7 US USA 840 1007 Bibb Alabama US 33.0
## 5 8.40e7 US USA 840 1009 Blount Alabama US 34.0
## 6 8.40e7 US USA 840 1011 Bullo… Alabama US 32.1
## 7 8.40e7 US USA 840 1013 Butler Alabama US 31.8
## 8 8.40e7 US USA 840 1015 Calho… Alabama US 33.8
## 9 8.40e7 US USA 840 1017 Chamb… Alabama US 32.9
## 10 8.40e7 US USA 840 1019 Chero… Alabama US 34.2
## # … with 3,330 more rows, and 247 more variables: Long_ <dbl>,
## # Combined_Key <chr>, `1/22/20` <dbl>, `1/23/20` <dbl>, `1/24/20` <dbl>,
## # `1/25/20` <dbl>, `1/26/20` <dbl>, `1/27/20` <dbl>, `1/28/20` <dbl>,
## # `1/29/20` <dbl>, `1/30/20` <dbl>, `1/31/20` <dbl>, `2/1/20` <dbl>,
## # `2/2/20` <dbl>, `2/3/20` <dbl>, `2/4/20` <dbl>, `2/5/20` <dbl>,
## # `2/6/20` <dbl>, `2/7/20` <dbl>, `2/8/20` <dbl>, `2/9/20` <dbl>,
## # `2/10/20` <dbl>, `2/11/20` <dbl>, `2/12/20` <dbl>, `2/13/20` <dbl>,
## # `2/14/20` <dbl>, `2/15/20` <dbl>, `2/16/20` <dbl>, `2/17/20` <dbl>,
## # `2/18/20` <dbl>, `2/19/20` <dbl>, `2/20/20` <dbl>, `2/21/20` <dbl>,
## # `2/22/20` <dbl>, `2/23/20` <dbl>, `2/24/20` <dbl>, `2/25/20` <dbl>,
## # `2/26/20` <dbl>, `2/27/20` <dbl>, `2/28/20` <dbl>, `2/29/20` <dbl>,
## # `3/1/20` <dbl>, `3/2/20` <dbl>, `3/3/20` <dbl>, `3/4/20` <dbl>,
## # `3/5/20` <dbl>, `3/6/20` <dbl>, `3/7/20` <dbl>, `3/8/20` <dbl>,
## # `3/9/20` <dbl>, `3/10/20` <dbl>, `3/11/20` <dbl>, `3/12/20` <dbl>,
## # `3/13/20` <dbl>, `3/14/20` <dbl>, `3/15/20` <dbl>, `3/16/20` <dbl>,
## # `3/17/20` <dbl>, `3/18/20` <dbl>, `3/19/20` <dbl>, `3/20/20` <dbl>,
## # `3/21/20` <dbl>, `3/22/20` <dbl>, `3/23/20` <dbl>, `3/24/20` <dbl>,
## # `3/25/20` <dbl>, `3/26/20` <dbl>, `3/27/20` <dbl>, `3/28/20` <dbl>,
## # `3/29/20` <dbl>, `3/30/20` <dbl>, `3/31/20` <dbl>, `4/1/20` <dbl>,
## # `4/2/20` <dbl>, `4/3/20` <dbl>, `4/4/20` <dbl>, `4/5/20` <dbl>,
## # `4/6/20` <dbl>, `4/7/20` <dbl>, `4/8/20` <dbl>, `4/9/20` <dbl>,
## # `4/10/20` <dbl>, `4/11/20` <dbl>, `4/12/20` <dbl>, `4/13/20` <dbl>,
## # `4/14/20` <dbl>, `4/15/20` <dbl>, `4/16/20` <dbl>, `4/17/20` <dbl>,
## # `4/18/20` <dbl>, `4/19/20` <dbl>, `4/20/20` <dbl>, `4/21/20` <dbl>,
## # `4/22/20` <dbl>, `4/23/20` <dbl>, `4/24/20` <dbl>, `4/25/20` <dbl>,
## # `4/26/20` <dbl>, `4/27/20` <dbl>, `4/28/20` <dbl>, …
head(time_series_confirmed_USA)
## # A tibble: 6 x 256
## UID iso2 iso3 code3 FIPS Admin2 Province_State Country_Region Lat
## <dbl> <chr> <chr> <dbl> <dbl> <chr> <chr> <chr> <dbl>
## 1 8.40e7 US USA 840 1001 Autau… Alabama US 32.5
## 2 8.40e7 US USA 840 1003 Baldw… Alabama US 30.7
## 3 8.40e7 US USA 840 1005 Barbo… Alabama US 31.9
## 4 8.40e7 US USA 840 1007 Bibb Alabama US 33.0
## 5 8.40e7 US USA 840 1009 Blount Alabama US 34.0
## 6 8.40e7 US USA 840 1011 Bullo… Alabama US 32.1
## # … with 247 more variables: Long_ <dbl>, Combined_Key <chr>, `1/22/20` <dbl>,
## # `1/23/20` <dbl>, `1/24/20` <dbl>, `1/25/20` <dbl>, `1/26/20` <dbl>,
## # `1/27/20` <dbl>, `1/28/20` <dbl>, `1/29/20` <dbl>, `1/30/20` <dbl>,
## # `1/31/20` <dbl>, `2/1/20` <dbl>, `2/2/20` <dbl>, `2/3/20` <dbl>,
## # `2/4/20` <dbl>, `2/5/20` <dbl>, `2/6/20` <dbl>, `2/7/20` <dbl>,
## # `2/8/20` <dbl>, `2/9/20` <dbl>, `2/10/20` <dbl>, `2/11/20` <dbl>,
## # `2/12/20` <dbl>, `2/13/20` <dbl>, `2/14/20` <dbl>, `2/15/20` <dbl>,
## # `2/16/20` <dbl>, `2/17/20` <dbl>, `2/18/20` <dbl>, `2/19/20` <dbl>,
## # `2/20/20` <dbl>, `2/21/20` <dbl>, `2/22/20` <dbl>, `2/23/20` <dbl>,
## # `2/24/20` <dbl>, `2/25/20` <dbl>, `2/26/20` <dbl>, `2/27/20` <dbl>,
## # `2/28/20` <dbl>, `2/29/20` <dbl>, `3/1/20` <dbl>, `3/2/20` <dbl>,
## # `3/3/20` <dbl>, `3/4/20` <dbl>, `3/5/20` <dbl>, `3/6/20` <dbl>,
## # `3/7/20` <dbl>, `3/8/20` <dbl>, `3/9/20` <dbl>, `3/10/20` <dbl>,
## # `3/11/20` <dbl>, `3/12/20` <dbl>, `3/13/20` <dbl>, `3/14/20` <dbl>,
## # `3/15/20` <dbl>, `3/16/20` <dbl>, `3/17/20` <dbl>, `3/18/20` <dbl>,
## # `3/19/20` <dbl>, `3/20/20` <dbl>, `3/21/20` <dbl>, `3/22/20` <dbl>,
## # `3/23/20` <dbl>, `3/24/20` <dbl>, `3/25/20` <dbl>, `3/26/20` <dbl>,
## # `3/27/20` <dbl>, `3/28/20` <dbl>, `3/29/20` <dbl>, `3/30/20` <dbl>,
## # `3/31/20` <dbl>, `4/1/20` <dbl>, `4/2/20` <dbl>, `4/3/20` <dbl>,
## # `4/4/20` <dbl>, `4/5/20` <dbl>, `4/6/20` <dbl>, `4/7/20` <dbl>,
## # `4/8/20` <dbl>, `4/9/20` <dbl>, `4/10/20` <dbl>, `4/11/20` <dbl>,
## # `4/12/20` <dbl>, `4/13/20` <dbl>, `4/14/20` <dbl>, `4/15/20` <dbl>,
## # `4/16/20` <dbl>, `4/17/20` <dbl>, `4/18/20` <dbl>, `4/19/20` <dbl>,
## # `4/20/20` <dbl>, `4/21/20` <dbl>, `4/22/20` <dbl>, `4/23/20` <dbl>,
## # `4/24/20` <dbl>, `4/25/20` <dbl>, `4/26/20` <dbl>, `4/27/20` <dbl>,
## # `4/28/20` <dbl>, …
time_series_confirmed_USA <- time_series_confirmed_USA %>%
select(-c(UID, iso2, iso3, code3, FIPS, Admin2, Combined_Key, Country_Region, Lat, Long_))
time_series_confirmed_USA <- time_series_confirmed_USA %>%
pivot_longer(-c(Province_State),
names_to = "Date", values_to = "Confirmed")
head(time_series_confirmed_USA)
## # A tibble: 6 x 3
## Province_State Date Confirmed
## <chr> <chr> <dbl>
## 1 Alabama 1/22/20 0
## 2 Alabama 1/23/20 0
## 3 Alabama 1/24/20 0
## 4 Alabama 1/25/20 0
## 5 Alabama 1/26/20 0
## 6 Alabama 1/27/20 0
Question 9
time_series_confirmed_USA %>%
group_by(Province_State) %>%
ggplot(aes(x= Date, y= Confirmed, color= Province_State)) +
geom_point() +
geom_line() +
ggtitle("Confirmed Cases in US States") +
theme(axis.text.x = element_text(colour = "black", size = 30, angle = 180, hjust = 2, vjust = 2), axis.text.y = element_text(colour = "black", size = 30), strip.text = element_text(face = "italic"), text = element_text(size = 30), axis.title.x = element_text(size = 80), axis.title.y = element_text(size = 80), plot.title = element_text(size = 125, face = "bold")) +
facet_wrap(~Province_State, ncol=2, scales="free_y") +
ylab("total Confirmed") +
xlab("per Day")
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?
